research projects
A Light Field Front-end for Robust SLAM in Dynamic Environments
Pushyami Kaveti
Dynamic Channel Selection in UAVs through Constellations in the Sky
Mithun Diddi
Multi-Sensor Mapping for Low Contrast, Quasi-Dynamic, Large Objects
Vikrant Shah

Iterative Labeling Process
Zhiyong Zhang, Samson Braun, Pushyami Kaveti
In this paper, we introduce a robust and cheap way to make training data set for object detection, especially for specialized fields that lack a large data set. The main idea of the Iterative Labeling Process is to train on predictions iteratively. Amazon MTurk is used to correct predictions. Auto-approval is applied to filter the MTurk results, which make the process fully automated. The process can save three times the common labeling cost. Furthermore, it can also complement missing objects and add ”background” labels in any existing data set. Train background labels can effectively reduce false positives.
Issues in the Design of Marine Vehicles: A Needs Based Analysis
Vikrant Shah
Towards A COLREGs Compliant Autonomous Surface Vessel
Zhiyong Zhang
In
Experimental Imaging Results of a UAV-mounted Downward-Looking mm-wave Radar
Mithun Diddi

Mobile Grasping & Tele-Operation
Penguin Counting with Machine Learning
Vikrant Shah
AirBeam: Experimental Demonstration of Distributed Beamforming by a Swarm of UAVs
Mithun Diddi
AutOTranS: An Autonomous Open World Transportation System
Vikrant Shah